> ## Documentation Index
> Fetch the complete documentation index at: https://www.edenai.co/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Haystack

> Use Eden AI with Haystack (deepset) to build LLM and RAG pipelines on 500+ AI models through one EU-hosted API key.

export const TechArticleSchema = ({title, description, path, articleSection, about, proficiencyLevel = "Beginner", dependencies, keywords = [], datePublished, dateModified, image, inLanguage = "en"}) => {
  const baseUrl = "https://www.edenai.co/docs";
  const canonicalUrl = `${baseUrl}/${path}`.replace(/\/+$/, "");
  const ogParams = new URLSearchParams({
    division: articleSection || "",
    title: title || "",
    description: description || ""
  });
  const resolvedImage = image || `https://edenai.mintlify.app/_mintlify/api/og?${ogParams.toString()}`;
  const data = {
    "@context": "https://schema.org",
    "@type": "TechArticle",
    "@id": `${canonicalUrl}#techarticle`,
    mainEntityOfPage: {
      "@type": "WebPage",
      "@id": canonicalUrl
    },
    headline: title,
    name: title,
    description: description,
    url: canonicalUrl,
    inLanguage: inLanguage,
    isPartOf: {
      "@type": "WebSite",
      name: "Eden AI Documentation",
      url: baseUrl
    },
    author: [{
      "@type": "Organization",
      name: "Eden AI",
      url: "https://www.edenai.co/"
    }],
    publisher: {
      "@type": "Organization",
      name: "Eden AI",
      url: "https://www.edenai.co/",
      logo: {
        "@type": "ImageObject",
        url: "https://www.edenai.co/assets/logo.png"
      }
    }
  };
  if (articleSection) data.articleSection = articleSection;
  if (about) data.about = {
    "@type": "Thing",
    name: about
  };
  if (proficiencyLevel) data.proficiencyLevel = proficiencyLevel;
  if (dependencies) data.dependencies = dependencies;
  if (keywords && keywords.length) data.keywords = keywords;
  if (datePublished) data.datePublished = datePublished;
  if (dateModified) data.dateModified = dateModified;
  data.image = Array.isArray(resolvedImage) ? resolvedImage : [resolvedImage];
  const json = JSON.stringify(data);
  const schemaId = `techarticle-${canonicalUrl}`;
  React.useEffect(() => {
    if (typeof document === "undefined") return;
    document.querySelectorAll(`script[data-schema-id="${schemaId}"]`).forEach(n => n.remove());
    const script = document.createElement("script");
    script.type = "application/ld+json";
    script.dataset.schemaId = schemaId;
    script.textContent = json;
    document.head.appendChild(script);
    return () => script.remove();
  }, [json, schemaId]);
  return null;
};

<TechArticleSchema title={"Haystack"} description={"Use Eden AI with Haystack (deepset) to build LLM and RAG pipelines on 500+ AI models through one EU-hosted API key."} path="v3/integrations/haystack" articleSection="AI Frameworks" about={"LLM Framework Integration"} proficiencyLevel="Intermediate" keywords={["Eden AI", "AI API", "Haystack", "deepset", "RAG", "Python"]} datePublished="2026-07-21T00:00:00Z" dateModified="2026-07-21T00:00:00Z" />

Use Eden AI with Haystack (deepset) to build LLM and RAG pipelines on 500+ AI models through one EU-hosted API key.

## Overview

[Haystack](https://haystack.deepset.ai/) is deepset's open-source Python framework for building production LLM applications, RAG pipelines and agents. **Eden AI ships as an official Haystack integration** (the `edenai-haystack` package), so your pipelines reach models from OpenAI, Anthropic, Google, Mistral and 500+ more behind one key, with EU-based, GDPR-aligned inference.

The integration provides three components:

* `EdenAIChatGenerator` for chat completion
* `EdenAITextEmbedder` to embed a query string
* `EdenAIDocumentEmbedder` to embed documents for indexing

Models use Eden AI's `provider/model` naming convention, for example `anthropic/claude-sonnet-4-5` or `mistral/mistral-large-latest`.

## Installation

<CodeGroup>
  ```bash pip theme={null}
  pip install edenai-haystack
  ```

  ```bash uv theme={null}
  uv add edenai-haystack
  ```
</CodeGroup>

## Quick Start

Set your key, then generate a chat response with the `EdenAIChatGenerator`:

<CodeGroup>
  ```bash .env theme={null}
  EDENAI_API_KEY=your_api_key_here
  ```

  ```python Python theme={null}
  from haystack.dataclasses import ChatMessage
  from haystack_integrations.components.generators.edenai import EdenAIChatGenerator

  generator = EdenAIChatGenerator(model="mistral/mistral-large-latest")

  response = generator.run([ChatMessage.from_user("What is Eden AI?")])
  print(response["replies"][0].text)
  ```
</CodeGroup>

The generator reads your key from the `EDENAI_API_KEY` environment variable by default.

## Switching models

Change providers by changing the `model` string. Every Eden AI model is reachable the same way:

<CodeGroup>
  ```python Python theme={null}
  from haystack.dataclasses import ChatMessage
  from haystack_integrations.components.generators.edenai import EdenAIChatGenerator

  messages = [ChatMessage.from_user("Write a haiku about the sea.")]

  for model in [
      "openai/gpt-4o-mini",
      "anthropic/claude-sonnet-4-5",
      "mistral/mistral-large-latest",
  ]:
      generator = EdenAIChatGenerator(model=model)
      print(model, "->", generator.run(messages)["replies"][0].text)
  ```
</CodeGroup>

## Streaming

Pass a `streaming_callback` to stream tokens as they are generated:

<CodeGroup>
  ```python Python theme={null}
  from haystack.components.generators.utils import print_streaming_chunk
  from haystack.dataclasses import ChatMessage
  from haystack_integrations.components.generators.edenai import EdenAIChatGenerator

  generator = EdenAIChatGenerator(
      model="mistral/mistral-large-latest",
      streaming_callback=print_streaming_chunk,
  )
  generator.run([ChatMessage.from_user("Count from one to five.")])
  ```
</CodeGroup>

## Embeddings and RAG

Use `EdenAITextEmbedder` to embed a query and `EdenAIDocumentEmbedder` to embed documents, so you can build a fully sovereign RAG stack (retrieval and generation) on EU-hosted models:

<CodeGroup>
  ```python Python theme={null}
  from haystack import Document
  from haystack.document_stores.in_memory import InMemoryDocumentStore
  from haystack.components.retrievers.in_memory import InMemoryEmbeddingRetriever
  from haystack_integrations.components.embedders.edenai import (
      EdenAIDocumentEmbedder,
      EdenAITextEmbedder,
  )

  document_store = InMemoryDocumentStore(embedding_similarity_function="cosine")

  # Index documents with their embeddings
  documents = [Document(content="Eden AI is a unified API for 500+ AI models.")]
  doc_embedder = EdenAIDocumentEmbedder(model="openai/text-embedding-3-small")
  document_store.write_documents(doc_embedder.run(documents)["documents"])

  # Embed the query and retrieve
  text_embedder = EdenAITextEmbedder(model="openai/text-embedding-3-small")
  retriever = InMemoryEmbeddingRetriever(document_store=document_store)
  query_embedding = text_embedder.run("What is Eden AI?")["embedding"]
  print(retriever.run(query_embedding=query_embedding)["documents"])
  ```
</CodeGroup>

## Available Models

Use the `provider/model` format for any Eden AI model:

**Chat**

* `openai/gpt-4o-mini`
* `anthropic/claude-sonnet-4-5`
* `mistral/mistral-large-latest`
* `google/gemini-2.5-flash`

**Embeddings**

* `openai/text-embedding-3-small`
* `mistral/mistral-embed`

Browse the full list in the [Eden AI models catalog](https://www.edenai.co/models).

## Environment Variables

<CodeGroup>
  ```bash .env theme={null}
  EDENAI_API_KEY=your_api_key_here
  ```
</CodeGroup>

## Next Steps

* [Chat Completions](/docs/v3/llms/chat-completions) - Core LLM endpoint
* [List LLM Models](/docs/v3/llms/listing-models) - Browse available providers and models
* [aisuite](/docs/v3/integrations/aisuite) - Another unified LLM interface
* [LangChain](/docs/v3/integrations/langchain) - Build LLM apps with LangChain